Lifestyle > Train of Thought

More Analysis on the 2004 Vote :)

<< < (7/10) > >>

Woodrow:
call me crazy, but isn't "130,000 to 260,000" a large gap for a "statistical study"???

acbaylove:

--- Quote from: Ant on November 19, 2004, 11:41:54 AM ---Is it true that Berlusconi was one a cruise ship singer? someone told me he was before.
--- End quote ---

Yeah, he still writes songs. He doesnt sing them, he has someone singing them. He writes. Love songs, using the dialect of Naples.

acbaylove:

--- Quote from: Woodrow on November 19, 2004, 11:58:34 AM ---call me crazy, but isn't "130,000 to 260,000" a large gap for a "statistical study"???
--- End quote ---

That's not even the point. The point is that them two number are based on two big "IF"...
IF.... then it's 130,000
IF.... then it's 260,000
IF NOT... then it's ok.

LOL.

Woodrow:
This "analysis" really isn't worth squat. I'm not surprised that Ant posted it.

These researchers (sociology students, not math students) used statistical models from the 2000, 1996 election, and didn't have NEARLY enough variables. As far as I could tell, they just left out the get-out-to-vote campaigns, issues that drew voters to the polls, age, religion, changes in voter registration population density, unemployment rate, etc...This paper hasn't even been published to journal yet. Therefore, it hasn't had any peer research/review. I could come out with a paper stating that I have conclusive proof that voter irregularities are caused by space aliens, but if I don't publicly release my methods and results, and have them reviewed, my paper isn't worth squat.

If one were to believe that this was a respectable study, one would have to believe that the 2000 election results were perfect. Ant and his wackjob supporters will tell you time and time again how Bush cheated in 2000.

You'd think this paper would look at Ohio, since it's the state with the most voter irregularities and the state that counted the "most" this election, but I'm willing to bet that the models they used didn't match up to the findings THEY were looking for. It's easy to see this paper was published to push forward an agenda. It's thinly disguised in simplified statistical models. It's clear this is biased because these people held a press conference BEFORE the peer review. Usually that's done AFTER the results of your research are substantiated.

I guess the new shit would be for us just not to vote at all because these statistical models can predict perfectly who we will vote for! What this paper really shows, is that you can't really predict the outcome of elections using ordinary-least-squares regression model (OLS) with and without robust standard errors.

I'll let one of Kerry's veteran camping advisors do the talking for me:

''No one would be more interested than me in finding out that we really won, but that ain't the case," said Jack Corrigan, a veteran Kerry adviser who led the Democrats' team of 3,600 attorneys who fanned out across the country on Election Day to address voting irregularities.

''I get why people are frustrated, but they did not steal this election," Corrigan said. ''There were a few problems here and there in the election. But unlike 2000, there is no doubt that they actually got more votes than we did, and they got them in the states that mattered."
http://www.boston.com/news/nation/articles/2004/11/10/internet_buzz_on_vote_fraud_is_dismissed/
 
In closing, Ant, you really think using statistical algorithm to predict an intelligent chaotic system will produce better results than the actual votes? Keep trying you fucking clown, it's time for you to crawl back into your little cave. Here's some free advice: go get some help. You're living in the past and pulling at strings that aren't there. You aren't living a healthy life. Faggot.

Ant:
do adding explicatives to your posts make you feel better? ah yes. how intelligent it must be to be a republican american.

Navigation

[0] Message Index

[#] Next page

[*] Previous page